new

Get trending papers in your email inbox once a day!

Get trending papers in your email inbox!

Daily Papers

by AK and the research community

Nov 21

Submitted by

jt-zhang

SageAttention2 Technical Report: Accurate 4 Bit Attention for Plug-and-play Inference Acceleration

·
6 authors

Submitted by

Ziqi

VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative Models

·
17 authors

Submitted by

Benjamin-eecs

Natural Language Reinforcement Learning

·
9 authors

Submitted by

teowu

VideoAutoArena: An Automated Arena for Evaluating Large Multimodal Models in Video Analysis through User Simulation

·
6 authors

Submitted by

wchai

SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory

·
5 authors

Submitted by

haonan3

When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training

·
7 authors

Submitted by

akhaliq

Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents

·
10 authors

Submitted by

CiaraRowles

Stylecodes: Encoding Stylistic Information For Image Generation

·
1 authors

Submitted by

amanchadha

ViBe: A Text-to-Video Benchmark for Evaluating Hallucination in Large Multimodal Models

·
12 authors

Submitted by

davidbrandfonbrener

Loss-to-Loss Prediction: Scaling Laws for All Datasets

·
5 authors

Submitted by

a-fontanella

Generating Compositional Scenes via Text-to-image RGBA Instance Generation

·
5 authors

Submitted by

Kaichengalex

ORID: Organ-Regional Information Driven Framework for Radiology Report Generation

·
6 authors